Spaces:
Runtime error
Runtime error
File size: 2,775 Bytes
9fcfc92 1459715 9fcfc92 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
import os
import shutil
from langchain.document_loaders.pdf import PyPDFDirectoryLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain.schema.document import Document
from get_embedding_function import get_embedding_function
from langchain.vectorstores.chroma import Chroma
CHROMA_PATH = "chroma"
DATA_PATH = "data"
def populate_database():
# Create (or update) the data store.
documents = load_documents()
chunks = split_documents(documents)
add_to_chroma(chunks)
def load_documents():
document_loader = PyPDFDirectoryLoader(DATA_PATH)
return document_loader.load()
def split_documents(documents: list[Document]):
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=800,
chunk_overlap=80,
length_function=len,
is_separator_regex=False,
)
return text_splitter.split_documents(documents)
def add_to_chroma(chunks: list[Document]):
# Load the existing database.
db = Chroma(
persist_directory=CHROMA_PATH, embedding_function=get_embedding_function()
)
# Calculate Page IDs.
chunks_with_ids = calculate_chunk_ids(chunks)
# Add or Update the documents.
existing_items = db.get(include=[]) # IDs are always included by default
existing_ids = set(existing_items["ids"])
print(f"Number of existing documents in DB: {len(existing_ids)}")
# Only add documents that don't exist in the DB.
new_chunks = []
for chunk in chunks_with_ids:
if chunk.metadata["id"] not in existing_ids:
new_chunks.append(chunk)
if len(new_chunks):
print(f"👉 Adding new documents: {len(new_chunks)}")
new_chunk_ids = [chunk.metadata["id"] for chunk in new_chunks]
db.add_documents(new_chunks, ids=new_chunk_ids)
db.persist()
else:
print("✅ No new documents to add")
def calculate_chunk_ids(chunks):
# This will create IDs like "data/monopoly.pdf:6:2"
# Page Source : Page Number : Chunk Index
last_page_id = None
current_chunk_index = 0
for chunk in chunks:
source = chunk.metadata.get("source")
page = chunk.metadata.get("page")
current_page_id = f"{source}:{page}"
# If the page ID is the same as the last one, increment the index.
if current_page_id == last_page_id:
current_chunk_index += 1
else:
current_chunk_index = 0
# Calculate the chunk ID.
chunk_id = f"{current_page_id}:{current_chunk_index}"
last_page_id = current_page_id
# Add it to the page meta-data.
chunk.metadata["id"] = chunk_id
return chunks
def clear_database():
if os.path.exists(CHROMA_PATH):
shutil.rmtree(CHROMA_PATH)
|